import pandas as pd
import seaborn as sns
import plotly.express as px

import matplotlib.pyplot as plt

import plotly.io as pio
pio.renderers.default = "plotly_mimetype+notebook"

Matplotlib

For this excercise, we have written the following code to load the stock dataset built into plotly express.

stocks = px.data.stocks()
stocks.head()

	date	GOOG	AAPL	AMZN	FB	NFLX	MSFT
0	2018-01-01	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000
1	2018-01-08	1.018172	1.011943	1.061881	0.959968	1.053526	1.015988
2	2018-01-15	1.032008	1.019771	1.053240	0.970243	1.049860	1.020524
3	2018-01-22	1.066783	0.980057	1.140676	1.016858	1.307681	1.066561
4	2018-01-29	1.008773	0.917143	1.163374	1.018357	1.273537	1.040708

Question 1:

Select a stock and create a suitable plot for it. Make sure the plot is readable with relevant information, such as date, values.

# axes x and y
x = stocks["date"]
y = stocks["GOOG"]

# initiate plot with title and labels

fig, ax = plt.subplots(1,1,figsize=(10,8))
ax.plot(x,y)
ax.set_title("Google stock")
ax.set_xlabel("date")
ax.set_ylabel("stock value")

# set the ticks on the x axis
xticks = ax.get_xticks()
new_xticks = xticks[0::14]
ax.set_xticks(new_xticks)

# show plot
plt.show

<function matplotlib.pyplot.show(close=None, block=None)>

Question 2:

You've already plot data from one stock. It is possible to plot multiples of them to support comparison.
To highlight different lines, customise line styles, markers, colors and include a legend to the plot.

# axes x and y
x = stocks["date"]
y1 = stocks["GOOG"]
y2 = stocks["AAPL"]
y3 = stocks["AMZN"]
y4 = stocks["FB"]
y5 = stocks["NFLX"]
y6 = stocks["MSFT"]

# initiate plots with title, labels, and legend
fig, ax = plt.subplots(1,1,figsize=(10,8))
ax.plot(x, y1, label = "GOOG")
ax.plot(x, y2, label = "AAPL")
ax.plot(x, y3, label = "AMZN")
ax.plot(x, y4, label = "FB")
ax.plot(x, y5, label = "NFLX")
ax.plot(x, y6, label = "MSFT")
ax.set_title("Stocks")
ax.set_xlabel("date")
ax.set_ylabel("stock value")
ax.legend()

# set the ticks on the x axis
xticks = ax.get_xticks()
new_xticks = xticks[0::14]
ax.set_xticks(new_xticks)

# show plot
plt.show

<function matplotlib.pyplot.show(close=None, block=None)>

Seaborn

First, load the tips dataset

tips = sns.load_dataset('tips')
tips.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

Question 3:

Let's explore this dataset. Pose a question and create a plot that support drawing answers for your question.

Some possible questions:

• Are there differences between male and female when it comes to giving tips?
• What attribute correlate the most with tip?

# Is there a correlation between day of the week and total bills paid?


df_thurs = tips[(tips['day'] == 'Thur')]
df_fri = tips[(tips['day'] == 'Fri')]
df_sat = tips[(tips['day'] == 'Sat')]
df_sun = tips[(tips['day'] == 'Sun')]

fig = plt.figure(figsize=(10,10))

gs = fig.add_gridspec(nrows=4, ncols=1)

ax = fig.add_subplot(gs[0,:])
ax.set_title('Thursday')
x = df_thurs['total_bill']
ax.set_ylabel('Frequency')
ax.set_xlabel('Total Bill')
ax.hist(x, bins=50, rwidth=0.8, color='g')

ax = fig.add_subplot(gs[1,:])
ax.set_title('Friday')
x = df_fri['total_bill']
ax.set_ylabel('Frequency')
ax.set_xlabel('Total Bill')
ax.hist(x, bins=50, rwidth=0.8, color='r')

ax = fig.add_subplot(gs[2,:])
ax.set_title('Saturday')
x = df_sat['total_bill']
ax.set_ylabel('Frequency')
ax.set_xlabel('Total Bill')
ax.hist(x, bins=50, rwidth=0.8, color='m')

ax = fig.add_subplot(gs[3,:])
ax.set_title('Sunday')
x = df_sun['total_bill']
ax.set_ylabel('Frequency')
ax.set_xlabel('Total Bill')
ax.hist(x, bins=50, rwidth=0.8, color = 'y')

fig.tight_layout()

# Joint plot
sns.jointplot(x='total_bill', y='day', data=tips)


plt.show()

Plotly Express

Question 4:

Redo the above exercises (challenges 2 & 3) with plotly express. Create diagrams which you can interact with.

The stocks dataset

Hints:

• Turn stocks dataframe into a structure that can be picked up easily with plotly express

fig = px.line(stocks, x="date", y=stocks.columns[1:7])
fig.show()

The tips dataset

df = px.data.tips()
fig = px.histogram(df, x="total_bill", color = "day")
fig.show()

Question 5:

Recreate the barplot below that shows the population of different continents for the year 2007.

Hints:

• Extract the 2007 year data from the dataframe. You have to process the data accordingly
• use plotly bar
• Add different colors for different continents
• Sort the order of the continent for the visualisation. Use axis layout setting
• Add text to each bar that represents the population

#load data
df = px.data.gapminder()
df.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4

# load 2007 data
df_2007 = df.query('year==2007')

# Sum up population by continent
df_sum = df_2007.groupby('continent').sum()

# Sort data into ascending order
df_sorted = df_sum.sort_values(by='pop',ascending=True)

# Create bar chart
fig = px.bar(df_sorted, x="pop", y=df_sum.index, 
             orientation='h', color = df_sum.index, 
             labels={'y':'continent','pop':'population'}, text = 'pop')
fig.show()